포지션 상세
About the Team & Mission
Physical AI Engineer는 차세대 자율주행을 위한 End-to-End(E2E) Planning Model을 설계·개발하고, 모델의 학습·검증을 위한 Closed-loop Simulation 환경과 파이프라인을 개발합니다.
Trajectory Generation과 Decision-making을 수행하는 E2E Planning Model부터 Closed-loop Simulation까지, 주행 상황을 바탕으로 안전한 의사결정과 trajectory를 생성하는 핵심 기술을 개발합니다. Generative AI, Imitation Learning, Reinforcement Learning, 3D 환경 재구성 및 물리 기반 Simulation 등 다양한 기술을 실제 Autonomous Driving 문제에 적용합니다.
E2E Planning Model을 직접 설계·개발하고, Closed-loop Simulation과 실차에서 성능을 검증합니다. Simulation 및 실차 주행 데이터와 실패 사례를 분석하여 모델을 개선하는 개발 사이클을 반복하며 차세대 Autonomous Driving System 개발에 기여합니다.
The Physical AI Engineer designs and develops end-to-end (E2E) planning models for next-generation autonomous driving, as well as closed-loop simulation environments and pipelines for training and validating them.
You will work with E2E planning models for trajectory generation and decision-making, closed-loop simulation, generative AI, imitation learning, reinforcement learning, 3D environment reconstruction, and physics-based simulation to solve real-world autonomous driving problems.
You will directly design and develop E2E planning models and validate their performance in closed-loop simulation and real vehicles. By analyzing simulation results, real-world driving data, and failure cases, you will continuously improve the models and contribute to next-generation autonomous driving systems.
• E2E Planning Model의 학습·검증을 위한 Closed-loop Simulation 환경, 시나리오 및 평가 Pipeline 설계·개발
• E2E Planning Model과 Simulation 및 실차 시스템 간 연동 기능 개발과 실차 실험 수행
• Simulation 결과와 실차 주행 데이터 및 실패 사례 분석을 통한 E2E Planning Model 개선
• Design and develop E2E planning models for trajectory generation and decision-making
• Design and develop closed-loop simulation environments, scenarios, and evaluation pipelines for training and validating E2E planning models
• Develop integrations between E2E planning models, simulation, and real-vehicle systems, and conduct real-vehicle experiments
• Improve E2E planning models by analyzing simulation results, real-world driving data, and failure cases
• Python 또는 C++을 활용하여 소프트웨어를 구현하고 디버깅한 경험
• 다음 분야 중 하나 이상에 대한 학업, 프로젝트 또는 실무 경험
- Machine Learning 또는 Deep Learning 모델 개발 및 학습
- Motion Planning, Decision-making 또는 Robotics 알고리즘
- Computer Vision 또는 3D 환경 재구성 및 표현
- 차량·로봇의 동역학 모델링 또는 Simulation
• Bachelor’s degree in Computer Science, Electrical Engineering, Automotive Engineering, Robotics, or a related field with 2+ years of professional experience, or equivalent practical expertise
• Experience implementing and debugging software using Python or C++
• Academic, project, or professional experience in at least one of the following areas:
- Machine learning or deep learning model development and training
- Motion planning, decision-making, or robotics algorithms
- Computer vision or 3D environment reconstruction and representation
- Vehicle or robot dynamics modeling or simulation
Physical AI Engineer는 차세대 자율주행을 위한 End-to-End(E2E) Planning Model을 설계·개발하고, 모델의 학습·검증을 위한 Closed-loop Simulation 환경과 파이프라인을 개발합니다.
Trajectory Generation과 Decision-making을 수행하는 E2E Planning Model부터 Closed-loop Simulation까지, 주행 상황을 바탕으로 안전한 의사결정과 trajectory를 생성하는 핵심 기술을 개발합니다. Generative AI, Imitation Learning, Reinforcement Learning, 3D 환경 재구성 및 물리 기반 Simulation 등 다양한 기술을 실제 Autonomous Driving 문제에 적용합니다.
E2E Planning Model을 직접 설계·개발하고, Closed-loop Simulation과 실차에서 성능을 검증합니다. Simulation 및 실차 주행 데이터와 실패 사례를 분석하여 모델을 개선하는 개발 사이클을 반복하며 차세대 Autonomous Driving System 개발에 기여합니다.
The Physical AI Engineer designs and develops end-to-end (E2E) planning models for next-generation autonomous driving, as well as closed-loop simulation environments and pipelines for training and validating them.
You will work with E2E planning models for trajectory generation and decision-making, closed-loop simulation, generative AI, imitation learning, reinforcement learning, 3D environment reconstruction, and physics-based simulation to solve real-world autonomous driving problems.
You will directly design and develop E2E planning models and validate their performance in closed-loop simulation and real vehicles. By analyzing simulation results, real-world driving data, and failure cases, you will continuously improve the models and contribute to next-generation autonomous driving systems.
주요업무
• Trajectory Generation 및 Decision-making을 위한 E2E Planning Model 설계 및 개발• E2E Planning Model의 학습·검증을 위한 Closed-loop Simulation 환경, 시나리오 및 평가 Pipeline 설계·개발
• E2E Planning Model과 Simulation 및 실차 시스템 간 연동 기능 개발과 실차 실험 수행
• Simulation 결과와 실차 주행 데이터 및 실패 사례 분석을 통한 E2E Planning Model 개선
• Design and develop E2E planning models for trajectory generation and decision-making
• Design and develop closed-loop simulation environments, scenarios, and evaluation pipelines for training and validating E2E planning models
• Develop integrations between E2E planning models, simulation, and real-vehicle systems, and conduct real-vehicle experiments
• Improve E2E planning models by analyzing simulation results, real-world driving data, and failure cases
자격요건
• 컴퓨터공학, 전자공학, 자동차공학, 로봇공학 또는 관련 분야의 학사 학위와 2년 이상의 실무 경험 또는 이에 준하는 역량• Python 또는 C++을 활용하여 소프트웨어를 구현하고 디버깅한 경험
• 다음 분야 중 하나 이상에 대한 학업, 프로젝트 또는 실무 경험
- Machine Learning 또는 Deep Learning 모델 개발 및 학습
- Motion Planning, Decision-making 또는 Robotics 알고리즘
- Computer Vision 또는 3D 환경 재구성 및 표현
- 차량·로봇의 동역학 모델링 또는 Simulation
• Bachelor’s degree in Computer Science, Electrical Engineering, Automotive Engineering, Robotics, or a related field with 2+ years of professional experience, or equivalent practical expertise
• Experience implementing and debugging software using Python or C++
• Academic, project, or professional experience in at least one of the following areas:
- Machine learning or deep learning model development and training
- Motion planning, decision-making, or robotics algorithms
- Computer vision or 3D environment reconstruction and representation
- Vehicle or robot dynamics modeling or simulation
